Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.4791. Min Act: -0.1700
Data Index: 8510353 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.4166. Min Act: -0.1700
Data Index: 6589876 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.3853. Min Act: -0.1700
Data Index: 7284133 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.3541. Min Act: -0.1700
Data Index: 1479118 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.2916. Min Act: -0.1700
Data Index: 5467331 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.2291. Min Act: -0.1700
Data Index: 2254981 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1978. Min Act: -0.1700
Data Index: 7880756 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1666. Min Act: -0.1700
Data Index: 8260110 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1353. Min Act: -0.1700
Data Index: 7384183 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1353. Min Act: -0.1700
Data Index: 8205856 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1353. Min Act: -0.1700
Data Index: 2700394 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.1041. Min Act: -0.1700
Data Index: 7880731 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0728. Min Act: -0.1700
Data Index: 7284135 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0728. Min Act: -0.1700
Data Index: 7880736 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0728. Min Act: -0.1700
Data Index: 4371530 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0728. Min Act: -0.1700
Data Index: 7880775 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0103. Min Act: -0.1700
Data Index: 3659705 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0416. Min Act: -0.1700
Data Index: 4230190 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0103. Min Act: -0.1700
Data Index: 7880747 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4791. Min Range: -6.4791
Max Act: 6.0416. Min Act: -0.1700
Data Index: 7567486 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19